• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.321-326
• /
• 2020

This paper is to analyze the language education policy in the context of multilingualism. As the majority of the population are multilingual, language policy should be centered on the multilingual speakers as the norm, and multilingual language policy is the best route which we can follow as a language policy in education. The motivation and legitimacy of the multilingual policies are suggested in terms of 6 different perspectives: identity, sustainability, equity, World Englishes, machine translation, and Universal Grammar (UG). As a model of language policy, the English-Plus (i.e., English+n) policy and similarly the Korean-Plus (i.e., Korean+n) policy are suggested to be the most appropriate language policies in the field of education in America and Korea respectively. These plus policies aim at bilingual fluency in both the native language and other foreign languages that are constitutive of the multilingualism of the country in which the bilingualism is treated as a variant of multilingualism. In a period of convergence and diversity in the 4^th Industrial Revolution, language diversity and multilingual policy should be considered as a right to be protected or as a resource to be conserved rather than as a problem to be solved.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.9-15
• /
• 2021

기계번역 품질 예측 (Quality Estimation, QE)은 정답 문장에 대한 참조없이 소스 문장과 기계번역 결과를 통해 기계번역 결과에 대한 품질을 수준별 주석으로 나타내주는 태스크이며, 다양한 활용도가 있다는 점에서 꾸준히 연구가 수행되고 있다. 그러나 QE 모델 학습을 위한 데이터 구성 시 기계번역 결과에 대해 번역 전문가가 교정한 문장이 필요한데, 이를 제작하는 과정에서 상당한 인건비와 시간 비용이 발생하는 한계가 있다. 본 논문에서는 번역 전문가 없이 병렬 또는 단일 말뭉치와 기계번역기만을 활용하여 자동화된 방식으로 한국어-영어 합성 QE 데이터를 구축하며, 최초로 단어 수준의 한국어-영어 기계번역 결과 품질 예측 모델을 제작하였다. QE 모델 제작 시에는 Cross-lingual language model (XLM), XLM-RoBERTa (XLM-R), multilingual BART (mBART)와 같은 다언어모델들을 활용하여 비교 실험을 수행했다. 또한 기계번역 결과에 대한 품질 예측의 객관성을 검증하고자 구글, 아마존, 마이크로소프트, 시스트란의 번역기를 활용하여 모델 평가를 진행했다. 실험 결과 XLM-R을 활용하여 미세조정학습한 QE 모델이 가장 좋은 성능을 보였으며, 품질 예측의 객관성을 확보함으로써 QE의 다양한 장점들을 한국어-영어 기계번역에서도 활용할 수 있도록 했다.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.35-43
• /
• 2021

Recently, there has been a growing interest in zero-shot cross-lingual transfer, which leverages cross-lingual language models (CLLMs) to perform downstream tasks that are not trained in a specific language. In this paper, we point out the limitations of the data-centric aspect of quality estimation (QE), and perform zero-shot cross-lingual transfer even in environments where it is difficult to construct QE data. Few studies have dealt with zero-shots in QE, and after fine-tuning the English-German QE dataset, we perform zero-shot transfer leveraging CLLMs. We conduct comparative analysis between various CLLMs. We also perform zero-shot transfer on language pairs with different sized resources and analyze results based on the linguistic characteristics of each language. Experimental results showed the highest performance in multilingual BART and multillingual BERT, and we induced QE to be performed even when QE learning for a specific language pair was not performed at all.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.21-29
• /
• 2022

Based on the importance of dialect research, preservation, and communication, this paper conducted a study on machine translation of Korean dialects for dialect users who may be marginalized. For the dialect data used, AIHUB dialect data distributed based on the highest administrative district was used. We propose a many-to-one dialect machine translation that promotes the efficiency of model distribution and modeling research to improve the performance of the dialect machine translation by applying Copy mechanism. This paper evaluates the performance of the one-to-one model and the many-to-one model as a BLEU score, and analyzes the performance of the many-to-one model in the Korean dialect from a linguistic perspective. The performance improvement of the one-to-one machine translation by applying the methodology proposed in this paper and the significant high performance of the many-to-one machine translation were derived.